Chris Olah
Opening the Black Box
Distill, feature visualisation and mechanistic interpretability
Rating
87Impact score
Domains
InterpretabilityVisualisationScientific communication
Scouting report
Did the feature-visualisation and circuits work that turned "what is the network doing" from a shrug into a research programme, and co-founded Distill to publish it in a form people could actually understand. Co-founded Anthropic, where the interpretability team continues to publish its findings openly.
Curator’s note
Made the insides of a model legible, and made the explanations beautiful.
Sources
- 01Distill distill.pub
- 02Zoom In: An Introduction to Circuits (2020) distill.pub